ArliAI_GLM-4.5-Air-Derestricted_REAP50_Creative

This is a 50% REAP of GLM-4.5-Air-Derestricted by ArliAI using a creative dataset, intended primarily for English language creative tasks in total memory-constrained environments.

It uses a MUCH smaller dataset than reported by cerebras here. Activations were recorded with seq length 3072, and the dataset itself is also considerably smaller. Custom patches were applied to make recording activations feasible on consumer hardware.
A sparse observer was utilized instead of materializing the entire [128, dim, tok] block when only top_k ones are actually routed.
The MTP layer was NOT pruned, and is currently excised from the model.

IT IS CURRENTLY UNTESTED

It may not load, may produce gibberish, or not quantize. I'll address these if revealed during testing.

REAM also in the oven c;

<div align="left"> <img src=https://cdn-uploads.huggingface.co/production/uploads/6625f4a8a8d1362ebcc3851a/iyzgR89q50pp1T8HeeP15.png width="5%"/> </div>

Arli AI

GLM-4.5-Air-Derestricted

<div align="center"> <img src=https://cdn-uploads.huggingface.co/production/uploads/6625f4a8a8d1362ebcc3851a/XhCz9N4liIwWEh-yH37gR.png width="15%"/> </div>

GLM-4.5-Air-Derestricted is a Derestricted version of GLM-4.5-Air, created by Arli AI.

Our goal with this release is to provide a version of the model that removed refusal behaviors while maintaining the high-performance reasoning of the original GLM-4.5-Air. This is unlike regular abliteration which often inadvertently "lobotomizes" the model.

Methodology: Norm-Preserving Biprojected Abliteration

To achieve this, Arli AI utilized Norm-Preserving Biprojected Abliteration, a refined technique pioneered by Jim Lai (grimjim). You can read the full technical breakdown in this article.

Why this matters:

Standard abliteration works by simply subtracting a "refusal vector" from the model's weights. While this works to uncensor a model, it is mathematically unprincipled. It alters the magnitude (or "loudness") of the neurons, destroying the delicate feature norms the model learned during training. This damage is why many uncensored models suffer from degraded logic or hallucinations.

How Norm-Preserving Biprojected Abliteration fixes it:

This model was modified using a three-step approach that removes refusals without breaking the model's brain:

1. Biprojection (Targeting): We refined the refusal direction to ensure it is mathematically orthogonal to "harmless" directions. This ensures that when we cut out the refusal behavior, we do not accidentally cut out healthy, harmless concepts.
2. Decomposition: Instead of a raw subtraction, we decomposed the model weights into Magnitude and Direction.
3. Norm-Preservation: We removed the refusal component solely from the directional aspect of the weights, then recombined them with their original magnitudes.

The Result:

By preserving the weight norms, we maintain the "importance" structure of the neural network. Benchmarks suggest that this method avoids the "Safety Tax"—not only effectively removing refusals but potentially improving reasoning capabilities over the baseline, as the model is no longer wasting compute resources on suppressing its own outputs.

In fact, you may find surprising new knowledge and capabilities that the original model does not initially expose.

Quantization:

• Original: https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted
• FP8: https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted-FP8
• INT8: https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted-W8A8-INT8
• W4A16: https://huggingface.co/ArliAI/GLM-4.5-Air-Derestricted-GPTQ-W4A16

---

Original model card:

<div align="center"> <img src=https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/logo.svg width="15%"/> </div> <p align="center"> 👋 Join our <a href="https://discord.gg/QR7SARHRxK" target="_blank">Discord</a> community. <br> 📖 Check out the GLM-4.5 <a href="https://z.ai/blog/glm-4.5" target="_blank">technical blog</a>, <a href="https://arxiv.org/abs/2508.06471" target="_blank">technical report</a>, and <a href="https://zhipu-ai.feishu.cn/wiki/Gv3swM0Yci7w7Zke9E0crhU7n7D" target="_blank">Zhipu AI technical documentation</a>. <br> 📍 Use GLM-4.5 API services on <a href="https://docs.z.ai/guides/llm/glm-4.5">Z.ai API Platform (Global)</a> or <br> <a href="https://docs.bigmodel.cn/cn/guide/models/text/glm-4.5">Zhipu AI Open Platform (Mainland China)</a>. <br> 👉 One click to <a href="https://chat.z.ai">GLM-4.5</a>. </p>

Model Introduction

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications.

Both GLM-4.5 and GLM-4.5-Air are hybrid reasoning models that provide two modes: thinking mode for complex reasoning and tool usage, and non-thinking mode for immediate responses.

We have open-sourced the base models, hybrid reasoning models, and FP8 versions of the hybrid reasoning models for both GLM-4.5 and GLM-4.5-Air. They are released under the MIT open-source license and can be used commercially and for secondary development.

As demonstrated in our comprehensive evaluation across 12 industry-standard benchmarks, GLM-4.5 achieves exceptional performance with a score of 63.2, in the 3rd place among all the proprietary and open-source models. Notably, GLM-4.5-Air delivers competitive results at 59.8 while maintaining superior efficiency.

For more eval results, show cases, and technical details, please visit our technical blog or technical report.

The model code, tool parser and reasoning parser can be found in the implementation of transformers, vLLM and SGLang.

Quick Start

Please refer our github page for more detail.